© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 43-GEMMASCOPE-2-TRANSCODER-262K
    7. 211162
    Prev
    Next
    INDEX
    Explanations

    valuable transferable skills

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_43_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Discipl
    0.47
     biosynthetic
    0.43
    ቀ
    0.41
    ClCompile
    0.40
     explanatory
    0.38
     kred
    0.38
     metabolic
    0.37
    otum
    0.37
    Dan
    0.37
     supervisory
    0.37
    POSITIVE LOGITS
     hard
    0.50
     Soft
    0.50
    Soft
    0.49
     सॉफ्ट
    0.48
     soft
    0.47
     Hard
    0.46
    soft
    0.46
    軟
    0.46
    硬
    0.45
     SOFT
    0.44
    Activations Density 0.006%

    No Known Activations